Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16723
    Prev
    Next
    INDEX
    Explanations

    the adjective "theoretical"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.84
     doctrine
    -0.81
    ronomy
    -0.79
     doctrines
    -0.79
    SpringBootTest
    -0.77
     Ono
    -0.68
     Bish
    -0.68
     philosophies
    -0.67
    новниш
    -0.67
     heresy
    -0.67
    POSITIVE LOGITS
    раздо
    0.64
     DataGridView
    0.60
     intelectual
    0.52
     Creamy
    0.52
    DECREF
    0.52
     hati
    0.51
    makeConstraints
    0.51
    原始内容存档于
    0.50
     Expend
    0.50
    SourceChecksum
    0.50
    Activations Density 0.008%

    No Known Activations